{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:47:35Z","timestamp":1778082455904,"version":"3.51.4"},"reference-count":67,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01978","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21299-21309","source":"Crossref","is-referenced-by-count":1,"title":["ETVA: Evaluation of Text-to-Video Alignment via Fine-Grained Question Generation and Answering"],"prefix":"10.1109","author":[{"given":"Kaisi","family":"Guan","sequence":"first","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengfeng","family":"Lai","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchong","family":"Sun","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kieran","family":"Liu","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Cao","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[{"name":"Renmin University of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","author":"Bansal","year":"2024","journal-title":"Videophy: Evaluating physical commonsense for video generation"},{"key":"ref2","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref3","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref4","article-title":"Interleaved scene graph for interleaved text-and-image generation assessment","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103581"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1267"},{"key":"ref7","article-title":"Davidsonian Scene Graph: Improving Reliability in Fine-Grained Evaluation for Text-to-Image Generation","author":"Cho","year":"2024","journal-title":"ICLR"},{"key":"ref8","author":"Clark","year":"2019","journal-title":"Adversarial video generation on complex datasets"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"ref10","article-title":"Vchitect-2.0: Parallel transformer for scaling up video diffusion models","author":"Fan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio","author":"J","year":"2014","journal-title":"Generative adversarial networks"},{"key":"ref12","article-title":"World models","author":"Ha","year":"2018","journal-title":"Zenodo"},{"key":"ref13","author":"Hong","year":"2022","journal-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01866"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref17","author":"Kingma","year":"2022","journal-title":"Auto-encoding variational bayes"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref19","author":"Kuaishou","year":"2024","journal-title":"Kling video generation"},{"key":"ref20","author":"Li","year":"2022","journal-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation"},{"key":"ref21","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01826"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3483"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref25","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref27","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref30","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref31","author":"Liu","year":"2024","journal-title":"A survey of ai-generated video evaluation"},{"key":"ref32","author":"Liu","year":"2023","journal-title":"Fetv: A benchmark for fine-grained evaluation of open-domain text-tovideo generation"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"ref34","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","author":"Meng","year":"2024","journal-title":"Towards world simulator: Crafting physical commonsense-based benchmark for video generation"},{"key":"ref36","author":"Meng","year":"2024","journal-title":"Towards world simulator: Crafting physical commonsense-based benchmark for video generation"},{"key":"ref37","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","first-page":"2024","article-title":"OpenAI","year":"2024","journal-title":"Gpt-4o"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref40","first-page":"311318","article-title":"Bleu: a method for automatic evaluation of machine translation","volume-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","author":"Papineni","year":"2002"},{"key":"ref41","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2022","journal-title":"arXiv preprint"},{"key":"ref42","author":"Radford","year":"2021","journal-title":"Learning transferable visual models from natural language supervision"},{"key":"ref43","article-title":"Dreamsync: Aligning text-to-image generation with image understanding feedback","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00787"},{"key":"ref45","article-title":"Diffusion model-based video editing: A survey","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","volume-title":"Mochi 1","author":"Team","year":"2024"},{"key":"ref47","year":"2024","journal-title":"Movie gen: A cast of media foundation models"},{"key":"ref48","article-title":"Pika Team","year":"2024","journal-title":"Pika"},{"key":"ref49","article-title":"Vidu Team","year":"2024","journal-title":"vidu"},{"key":"ref50","article-title":"Atom of thoughts for markov 11 m test-time scaling","author":"Teng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","author":"van den Oord","journal-title":"Neural discrete representation learning 2018"},{"key":"ref54","author":"Wang","year":"2023","journal-title":"Modelscope text-to-video technical report"},{"key":"ref55","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","author":"Wang","year":"2024","journal-title":"Internvid: A large-scale video-text dataset for multi-modal understanding and generation"},{"key":"ref57","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref58","author":"Yan","year":"2021","journal-title":"Videogpt: Video generation using vq-vae and transformers"},{"key":"ref59","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Chronomagic-bench: A benchmark for metamorphic evaluation of text-to-time-lapse video generation","author":"Yuan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","author":"Zeng","year":"2024","journal-title":"The dawn of video generation: Preliminary explorations with sora-like models"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00845"},{"key":"ref64","article-title":"Video instruction tuning with synthetic data","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612707"},{"key":"ref67","article-title":"Lienkamp, Thomas Brox, and Olaf Ronneberger","author":"\u00c7i\u00e7ek","year":"2016","journal-title":"3d u-net: Learning dense volumetric segmentation from sparse annotation"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445108.pdf?arnumber=11445108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:34Z","timestamp":1777529914000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01978","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}